signoz-reducing-telemetry-cost

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The required runtime workflow ingests SigNoz MCP tool outputs (e.g., metric field keys, alert rule filters, and sampled log bodies) into the agent’s context; these tool results can include outsider-authored free text such as log body/exception messages/attribute values, creating an indirect prompt-injection risk.